Abstract:In this paper, we present an Extended Kalman Filter (EKF)-based algorithm for real-time vision-aided inertial navigation. The primary contribution of this work is the derivation of a measurement model that is able to express the geometric constraints that arise when a static feature is observed from multiple camera poses. This measurement model does not require including the 3D feature position in the state vector of the EKF and is optimal, up to linearization errors. The vision-aided inertial navigation algor… Show more
“…However, we do not store OFs in the map. Instead, all OFs are processed and marginalized on-the-fly using the MSC-KF approach [25] (see Sect. 3.2).…”
Section: System State and Propagation Modelmentioning
confidence: 99%
“…Finally, for OFs, we employ the MSC-KF approach [25] to impose a pose update constraining all the views from which the feature was seen. To accomplish this, we utilize stochastic cloning [29] over a window of m camera poses.…”
Section: Measurement Update Modelmentioning
confidence: 99%
“…The first block column of (25) requires that H f = −H p I . Hence, we rewrite the second block column of (25) as…”
In this paper, we study estimator inconsistency in Vision-aided Inertial Navigation Systems (VINS) from a standpoint of system observability. We postulate that a leading cause of inconsistency is the gain of spurious information along unobservable directions, resulting in smaller uncertainties, larger estimation errors, and possibly even divergence. We develop an Observability-Constrained VINS (OC-VINS), which explicitly enforces the unobservable directions of the system, hence preventing spurious information gain and reducing inconsistency. Our analysis, along with the proposed method for reducing inconsistency, are extensively validated with simulation trials and real-world experiments.
“…However, we do not store OFs in the map. Instead, all OFs are processed and marginalized on-the-fly using the MSC-KF approach [25] (see Sect. 3.2).…”
Section: System State and Propagation Modelmentioning
confidence: 99%
“…Finally, for OFs, we employ the MSC-KF approach [25] to impose a pose update constraining all the views from which the feature was seen. To accomplish this, we utilize stochastic cloning [29] over a window of m camera poses.…”
Section: Measurement Update Modelmentioning
confidence: 99%
“…The first block column of (25) requires that H f = −H p I . Hence, we rewrite the second block column of (25) as…”
In this paper, we study estimator inconsistency in Vision-aided Inertial Navigation Systems (VINS) from a standpoint of system observability. We postulate that a leading cause of inconsistency is the gain of spurious information along unobservable directions, resulting in smaller uncertainties, larger estimation errors, and possibly even divergence. We develop an Observability-Constrained VINS (OC-VINS), which explicitly enforces the unobservable directions of the system, hence preventing spurious information gain and reducing inconsistency. Our analysis, along with the proposed method for reducing inconsistency, are extensively validated with simulation trials and real-world experiments.
“…Visual-inertial odometry with a translational error in the range of 1% of the distance traveled (similar to [29]) was used to construct the maps. Keypoints were detected using a Difference of Gaussians (DoG) keypoint detector.…”
Figure 1: An overview of the proposed algorithm: A classifier is used to decide whether a particular visual feature is expected to be persistent or not. Our method uses full image information as input and helps to maintain compact stable-over-time maps that can be used for life-long localization.
AbstractAn increasing number of simultaneous localization and mapping (SLAM) systems are using appearance-based localization to improve the quality of pose estimates. However, with the growing time-spans and size of the areas we want to cover, appearance-based maps are often becoming too large to handle and are consisting of features that are not always reliable for localization purposes. This paper presents a method for selecting map features that are persistent over time and thus suited for long-term localization. Our methodology relies on a CNN classifier based on image patches and depth maps for recognizing which features are suitable for life-long matchability. Thus, the classifier not only considers the appearance of a feature but also takes into account its expected lifetime. As a result, our feature selection approach produces more compact maps with a high fraction of temporally-stable features compared to the current state-of-the-art, while rejecting unstable features that typically harm localization. Our approach is validated on indoor and outdoor datasets, that span over a period of several months.
“…The rich representation of a scene captured in an image, together with the accurate short-term estimates by gyroscopes and accelerometers present in a typical IMU have been acknowledged to complement each other, with great uses in airborne [6,20] and automotive [14] navigation. Moreover, with the availability of these sensors in most smart phones, there is great interest and research activity in effective solutions to visual-inertial SLAM.…”
Abstract-The fusion of visual and inertial cues has become popular in robotics due to the complementary nature of the two sensing modalities. While most fusion strategies to date rely on filtering schemes, the visual robotics community has recently turned to non-linear optimization approaches for tasks such as visual Simultaneous Localization And Mapping (SLAM), following the discovery that this comes with significant advantages in quality of performance and computational complexity. Following this trend, we present a novel approach to tightly integrate visual measurements with readings from an Inertial Measurement Unit (IMU) in SLAM. An IMU error term is integrated with the landmark reprojection error in a fully probabilistic manner, resulting to a joint non-linear cost function to be optimized. Employing the powerful concept of 'keyframes' we partially marginalize old states to maintain a bounded-sized optimization window, ensuring real-time operation. Comparing against both vision-only and loosely-coupled visual-inertial algorithms, our experiments confirm the benefits of tight fusion in terms of accuracy and robustness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.